 |
 | Home | Contact Us | FAQ | Search & Site Map | Link to Us |
 | Sign In | Join | Other 45 Sites in Network |
Math Forum / Math Software / MATLAB / July 2008pdf with skew and kurtosis
Hi, How do I generate a pdf, given its mean, std, skew and kurtosis ? The function 'gevpdf' (statistical toolbox) does this for a given mean, std and skew. The function 'gevfit' fits a model of three parameters (mean, std, skew) to any data. I'm looking for an extension that also includes an additional parameter kurtosis. Online search directs me to terms like - matching moments, edgeworth series, etc; Is there a matlab implementation of these methods? Thanks, Sachin > Hi, > [quoted text clipped - 3 lines] > mean, std and skew. The function 'gevfit' fits a model of three > parameters (mean, std, skew) to any data. That's not exactly true, the GEV dist'n is not parameterized in terms of (mean,std,skew), at least not in the Statistics Toolbox. Of course you can transform the parameters into that, which is what GEVSTAT does. > I'm looking for an extension > that also includes an additional parameter kurtosis. See PEARSRND and JOHNSRND. They are nominally intended for generating random values (which may be what you want anyway), but you can use the second and third outputs to, in effect, fit to data. In the case of PEARSRND, you'll have to poke around a little in the code to see how the third output is related to a specific PDF, but it's all pretty clear in there. Hope this helps. - Peter Perkins The MathWorks, Inc. Hi Peter, Thanks for the response. This helps a bit. I will look at PEARSRND and JOHNSRND. What I'm really looking for is to overlay a pdf on a histogram. Given some data, I used GEVFIT and GEVPDF to do this. The overlayed pdf seemed to lack shape. I wanted to take this a step further and use all four moments - mean, std, skew and kurtosis. Thanks, Sachin |
Reply to this Message |
 Sign In
 Join
 My Latest Posts My Monitored Threads My Blog My Photo Gallery My Profile My Homepage Start New Thread Enable EMail Alerts Rate this Thread
|
©2010 Advenet LLC Privacy Policy - Terms of Use
This website includes both content owned or controlled by Advenet as well as content owned or controlled by third parties.